EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MIRAGE-DTA: conflict-aware multimodal evidence arbitration for drug–target affinity prediction

Shenkuang Wu, Jing Zhang, Lianming Zhang, Pingping Dong

Bioinformatics · 10.11.2026

DOI: 10.1093/bioinformatics/btag812 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 10.11.2026. Verfasst von Shenkuang Wu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Hunan Normal University, Changsha, China. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Multimodal drug–target affinity (DTA) models can incorporate molecular, protein, assay and textual evidence whose availability and reliability vary under missing modalities, cold-start entities and assay distribution shift. Results We present MIRAGE-DTA, a reliability-oriented evidence-arbitration layer that complements DTA encoders by keeping current-sample and training-set retrieval evidence as two explicit chains, carrying modality masks into fusion, retrieving training-only neighbors, and resolving disagreement with an interaction gate and validation-selected anchor. Across BindingDB_Kd, DAVIS, KIBA and a 2010–2024 CHEMBL_ASSAY benchmark with 35,238 interactions, experiments tested cold-start, missing-modality and assay/temporal shift settings. Under 35% sequence/text missingness on CHEMBL_ASSAY, 10-seed paired evaluation showed that MIRAGE-DTA reduced expected calibration error relative to late fusion by 0.0524, 0.0923 and 0.1018 on assay-cold, target-cold and temporal splits. Risk at 80% coverage was significantly lower on target-cold and temporal splits and numerically lower on assay-cold. A complementary complete-evidence direct-pChEMBL regression analysis also showed lower RMSE for the two-branch model than for current-only and retrieval-only regressors across assay-cold, target-cold and temporal splits. Ranking remained broadly competitive, with a modest trade-off on the temporal split, indicating that the principal benefit lies in calibrated and selective prediction under incomplete or shifted evidence. Shortcut audits quantified neighbor-overlap effects and showed that temporal retrieval was not driven by repeated compounds or near-duplicate scaffolds. Availability and implementation Source code is available at https://github.com/wushen1103-collab/mirage_drug_miniprototype and archived on Zenodo at https://doi.org/10.5281/zenodo.22695984; data come from public sources.

Schlagwörter

Stichwörter der Autor:innen

distribution shiftdrug–target affinity predictionmissing modalitiesmultimodal information fusionreliability calibrationretrieval-augmented learning

Autor:innen und Institutionen

  • School of Information Science and Engineering, Hunan Normal University, Changsha, China.
  • Faculty of Medicine, Hunan Normal University, Changsha, China.
  • Xiangjiang Laboratory, Changsha, China.

Zitieren

APA

Wu, S., Zhang, J., Zhang, L., & Dong, P. (2026). MIRAGE-DTA: conflict-aware multimodal evidence arbitration for drug–target affinity prediction. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag812

Vancouver

Wu S, Zhang J, Zhang L, Dong P. MIRAGE-DTA: conflict-aware multimodal evidence arbitration for drug–target affinity prediction. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag812

BibTeX
@article{Wu2026,
  author = {Wu, Shenkuang and Zhang, Jing and Zhang, Lianming and Dong, Pingping},
  title = {MIRAGE-DTA: conflict-aware multimodal evidence arbitration for drug–target affinity prediction},
  journal = {Bioinformatics},
  year = {2026},
  doi = {10.1093/bioinformatics/btag812}
}
Kostenlos starten →